# Accelerating attention through gradient-based learned runtime pruning

> Research article (Proceedings of the 49th Annual International Symposium on Computer Architecture, 2022) · cited 46× · AI/ML

**Wikidata**: [openalex:W4224267386](https://www.wikidata.org/wiki/openalex:W4224267386)  
**Source**: https://4ort.xyz/entity/accelerating-attention-through-gradient-based-learned-runtime-pruning